Waviness measurement precision correction method and system based on artificial intelligence

Abstract

The invention relates to the technical field of artificial intelligence engineering, in particular to a waviness measurement precision correction method and system based on artificial intelligence, and the method comprises the steps: obtaining the dynamic process parameters of a machine tool and the waviness feature data of a workpiece when the machine tool machines the workpiece, and constructing a causal structure map; environment influence data and surface waviness data of the workpiece are collected in real time, whether the surface waviness data exceed a preset waviness threshold value or not is judged, and if yes, waviness abnormal data are obtained; inputting the waviness abnormal data into a causal structure map to obtain an influence path of a main process factor and an influence path of a secondary process factor; and generating a waviness correction value to obtain a waviness correction value. According to the method, a solid foundation is provided for subsequent correction by constructing the causal structure map, the correction result is enabled to better conform to the waviness condition in the actual processing environment by comprehensively considering the environmental influence data, and the practicability and adaptability of the correction method are enhanced.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence engineering technology, and particularly to a method and system for correcting the measurement accuracy of waviness based on artificial intelligence. Background Art

[0002] The waviness of a workpiece surface refers to a periodic or quasi-periodic geometric shape deviation that appears on the workpiece surface between the macroscopic shape error and the microscopic roughness after machining, and is one of the key indicators for measuring machining quality. Accurately correcting the measurement accuracy of waviness can more accurately reflect the actual surface quality of the workpiece. This helps machining enterprises to strictly control product quality, making the produced parts more in line with design requirements and usage standards, reducing defective products caused by unqualified waviness, improving the overall performance and durability of products, and is crucial for producing high-precision mechanical parts, aerospace components, etc. in the field of mechanical manufacturing, directly affecting the reliability and safety of products.

[0003] However, traditional methods usually simply eliminate or smooth the measurement data afterwards, and cannot accurately identify the main process factors and causal influence paths that cause anomalies, so it is difficult to take effective corrective measures from the source. Therefore, it is easy for the corrected waviness data to still deviate from the actual situation, affecting the accurate evaluation and control of the machining process. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and system for correcting the measurement accuracy of waviness based on artificial intelligence that can improve data processing efficiency for the above technical problems.

[0005] The technical solution of the present invention is as follows: A method for correcting the measurement accuracy of waviness based on artificial intelligence, the method comprising: Obtaining the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, and constructing a causal structure map according to the dynamic process parameters and the waviness characteristic data; Real-time collecting environmental impact data and the surface waviness data of the workpiece, and determining whether the surface waviness data exceeds a preset waviness threshold. If the determination is yes, waviness abnormal data is obtained; Inputting the waviness abnormal data into the causal structure map, analyzing the waviness abnormal data based on the causal structure map, and obtaining the influence path of the main process factor and the influence path of the secondary process factor; Generating a waviness correction value according to the main process factor and the influence path of the main process factor, and calculating a waviness correction value according to the environmental impact data and the waviness correction value.

[0006] Specifically, input the waviness anomaly data into the causal structure map, analyze the waviness anomaly data based on the causal structure map, and obtain the influence paths of the main process factors and the influence paths of the secondary process factors, including: Input the waviness anomaly data into the causal structure map, and use the graph convolutional network method in the causal structure map for reverse reasoning to obtain the process parameter responsibility factors. Use the Bayesian inference method to screen the process parameter responsibility factors to obtain the main process factors and the secondary process factors. By querying the causal structure map, respectively obtain the influence paths of the main process factors and the influence paths of the secondary process factors.

[0007] Specifically, according to the main process factors and the influence paths of the main process factors, generate a waviness correction value, including: According to the main process factors and the influence paths of the main process factors, generate a main cause correction value through the adaptive projection algorithm. According to the secondary process factors and the influence paths of the secondary process factors, calculate and generate a secondary cause correction value through the adaptive projection algorithm. According to the main cause correction value and the secondary cause correction value, calculate and obtain the waviness correction value.

[0008] Specifically, calculate and obtain the waviness correction value according to the environmental impact data and the waviness correction value, including: Generate an environmental impact coefficient according to the environmental impact data. Calculate and obtain an environmental compensation value according to the influence degree of the environmental impact coefficient on the waviness. Calculate and obtain the waviness correction value according to the waviness correction value and the environmental compensation value.

[0009] Specifically, generate an environmental impact coefficient according to the environmental impact data, including: Perform standardization processing on the environmental impact data and generate standardized environmental data. Generate an environmental impact coefficient based on the preset Gaussian process regression and the standardized environmental data.

[0010] Specifically, obtain the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, and construct a causal structure map according to the dynamic process parameters and the waviness characteristic data, including: Obtain the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, calculate the correlation between the dynamic process parameters and the waviness characteristic data through the multi-head graph attention layer method, and obtain the edge weight coefficient. Construct a causal structure map according to the dynamic process parameters, the waviness characteristic data, and the edge weight coefficients.

[0011] Specifically, after determining whether the surface waviness data exceeds a preset waviness threshold, the following steps are further included: If the determination result is negative, it is determined that the surface waviness data is normal.

[0012] Specifically, an artificial intelligence-based waviness measurement accuracy correction system, the system includes: A causal map construction module, configured to obtain the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, and construct a causal structure map according to the dynamic process parameters and the waviness characteristic data; An abnormal data acquisition module, configured to collect environmental impact data and the surface waviness data of the workpiece in real time, determine whether the surface waviness data exceeds a preset waviness threshold, and if the determination result is positive, obtain waviness abnormal data; An abnormal data analysis module, configured to input the waviness abnormal data into the causal structure map, analyze the waviness abnormal data based on the causal structure map, and obtain the influence paths of the main process factors and the influence paths of the secondary process factors; An environmental impact correction module, configured to generate a waviness correction value according to the main process factor and the influence path of the main process factor, and calculate a waviness correction value according to the environmental impact data and the waviness correction value.

[0013] Specifically, the abnormal data analysis module is further configured to: input the waviness abnormal data into the causal structure map, perform reverse reasoning in the causal structure map using the graph convolutional network method to obtain process parameter responsibility factors; use the Bayesian inference method to screen the process parameter responsibility factors to obtain the main process factors and the secondary process factors; respectively obtain the influence paths of the main process factors and the influence paths of the secondary process factors by querying the causal structure map.

[0014] Specifically, the environmental impact correction module is further configured to: generate a main cause correction value through an adaptive projection algorithm according to the main process factor and the influence path of the main process factor; calculate and generate a secondary cause correction value through an adaptive projection algorithm according to the secondary process factor and the influence path of the secondary process factor; calculate a waviness correction value according to the main cause correction value and the secondary cause correction value.

[0015] Specifically, the environmental impact correction module is further configured to: generate an environmental impact coefficient according to the environmental impact data; calculate an environmental compensation value according to the influence degree of the environmental impact coefficient on the waviness; calculate a waviness correction value according to the waviness correction value and the environmental compensation value.

[0016] Specifically, the environmental impact correction module is further configured to: normalize the environmental impact data and generate normalized environmental data; generate an environmental impact coefficient based on a preset Gaussian process regression and the normalized environmental data.

[0017] Specifically, the causal graph construction module is further configured to: obtain the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, calculate the correlation between the dynamic process parameters and the waviness characteristic data by the multi-head graph attention layer method to obtain an edge weight coefficient; construct a causal structure graph according to the dynamic process parameters, the waviness characteristic data and the edge weight coefficient.

[0018] Specifically, the abnormal data acquisition module is further configured to: determine whether the surface waviness data exceeds a preset waviness threshold, and then, if the determination result is negative, determine that the surface waviness data is normal.

[0019] Optionally, a computer device is further provided, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned waviness measurement accuracy correction method based on artificial intelligence are implemented.

[0020] Optionally, a computer-readable storage medium is further provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned waviness measurement accuracy correction method based on artificial intelligence are implemented.

[0021] The present invention relates to deep learning and deep neural network technologies, and its technical effects are as follows: The above-mentioned artificial intelligence-based corrugation measurement accuracy correction method and system successively obtain the dynamic process parameters of the machine tool and the corrugation characteristic data of the workpiece when the machine tool processes the workpiece, and construct a causal structure map according to the dynamic process parameters and the corrugation characteristic data; collect environmental impact data and surface corrugation data of the workpiece in real time, and judge whether the surface corrugation data exceeds a preset corrugation threshold, and if it is judged as yes, obtain corrugation abnormality data; input the corrugation abnormality data into the causal structure map, analyze the corrugation abnormality data based on the causal structure map, and obtain the influence path of the main process factors and the influence path of the secondary process factors; generate a corrugation correction value according to the main process factors and the influence path of the main process factors, and calculate the corrugation correction value according to the environmental impact data and the corrugation correction value. On the one hand, this application obtains rich dynamic process parameters and waviness feature data, uses advanced algorithms such as multi-head graph attention layer method, accurately calculates the correlation between process parameters and waviness feature data, constructs causal structure map, provides a solid foundation for subsequent correction, can effectively reduce measurement errors, improve the accuracy of waviness measurement, and make the measurement results closer to the actual surface waviness of the workpiece. On the other hand, by accurately determining the abnormality of waviness, and starting from the abnormal node, through graph convolution operation and Bayesian reasoning, in-depth analysis is conducted to find out the main and secondary process factors and their causal influence paths that cause the abnormality, and the correction amount of the main cause and the secondary cause is calculated in a targeted manner, so as to achieve effective correction of the waviness abnormality, improve the stability and reliability of the production process, and reduce the production interruption and defective rate caused by waviness problems. In addition, by comprehensively considering environmental impact data, including humidity, cutting fluid performance and viscosity, calculating the environmental impact coefficient and combining it with the correction value, it fully makes up for the deficiency of traditional methods that ignore environmental factors, so that the correction results are more in line with the waviness conditions under the actual processing environment, and enhances the practicality and adaptability of the correction method. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of a flow chart of a method for correcting waviness measurement accuracy based on artificial intelligence in one embodiment; Figure 2 The structure block diagram of a corrugation measurement accuracy correction system based on artificial intelligence in one embodiment. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0024] It should be understood that, as used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups.

[0025] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] As used in the specification of the present application and the appended claims, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrases "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]".

[0027] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0028] Reference to "one embodiment" or "some embodiments" or the like described in the specification of the present application means that a particular feature, structure or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0029] In one embodiment, a terminal is provided, and the terminal is configured to: obtain the dynamic process parameters of a machine tool and the waviness characteristic data of a workpiece when the machine tool processes the workpiece, and construct a causal structure map according to the dynamic process parameters and the waviness characteristic data; collect the environmental impact data and the surface waviness data of the workpiece in real time, determine whether the surface waviness data exceeds a preset waviness threshold, and if the determination is yes, obtain waviness abnormal data; input the waviness abnormal data into the causal structure map, analyze the waviness abnormal data based on the causal structure map, and obtain the influence paths of the main process factors and the influence paths of the secondary process factors; generate a waviness correction value according to the main process factors and the influence paths of the main process factors, and calculate a waviness correction value according to the environmental impact data and the waviness correction value.

[0030] The terminal may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices.

[0031] In one embodiment, as Figure 1 shown, a method for correcting the measurement accuracy of waviness based on artificial intelligence is provided, and the method includes: Step S100: Obtain the dynamic process parameters of a machine tool and the waviness characteristic data of a workpiece when the machine tool processes the workpiece, and construct a causal structure map according to the dynamic process parameters and the waviness characteristic data; Step S200: Collect the environmental impact data and the surface waviness data of the workpiece in real time, determine whether the surface waviness data exceeds a preset waviness threshold, and if the determination is yes, obtain waviness abnormal data; Step S300: Input the waviness abnormal data into the causal structure map, analyze the waviness abnormal data based on the causal structure map, and obtain the influence paths of the main process factors and the influence paths of the secondary process factors; Step S400: Generate a waviness correction value according to the main process factors and the influence paths of the main process factors, and calculate a waviness correction value according to the environmental impact data and the waviness correction value.

[0032] In this embodiment, the dynamic process parameters of the machine tool and the corrugation characteristic data of the workpiece are acquired in sequence when the machine tool processes the workpiece, and a causal structure map is constructed according to the dynamic process parameters and the corrugation characteristic data; environmental impact data and surface corrugation data of the workpiece are collected in real time to determine whether the surface corrugation data exceeds a preset corrugation threshold, and if so, abnormal corrugation data is obtained; the abnormal corrugation data is input into the causal structure map, and the abnormal corrugation data is analyzed based on the causal structure map, and the influence path of the main process factor and the influence path of the secondary process factor are obtained; a corrugation correction value is generated according to the main process factor and the influence path of the main process factor, and a corrugation correction value is calculated according to the environmental impact data and the corrugation correction value. On the one hand, this application obtains rich dynamic process parameters and waviness feature data, uses advanced algorithms such as multi-head graph attention layer method, accurately calculates the correlation between process parameters and waviness feature data, constructs causal structure map, provides a solid foundation for subsequent correction, can effectively reduce measurement errors, improve the accuracy of waviness measurement, and make the measurement results closer to the actual surface waviness of the workpiece. On the other hand, by accurately determining the abnormality of waviness, and starting from the abnormal node, through graph convolution operation and Bayesian reasoning, in-depth analysis is conducted to find out the main and secondary process factors and their causal influence paths that cause the abnormality, and the correction amount of the main cause and the secondary cause is calculated in a targeted manner, so as to achieve effective correction of the waviness abnormality, improve the stability and reliability of the production process, and reduce the production interruption and defective rate caused by waviness problems. In addition, by comprehensively considering environmental impact data, including humidity, cutting fluid performance and viscosity, calculating the environmental impact coefficient and combining it with the correction value, it fully makes up for the deficiency of traditional methods that ignore environmental factors, so that the correction results are more in line with the waviness conditions under the actual processing environment, and enhances the practicality and adaptability of the correction method.

[0033] In one embodiment, step S100: obtaining dynamic process parameters of a machine tool and waviness characteristic data of a workpiece when the machine tool processes the workpiece, and constructing a causal structure graph according to the dynamic process parameters and the waviness characteristic data; comprising: Step S110: obtaining the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, calculating the correlation between the dynamic process parameters and the waviness characteristic data by using the multi-head graph attention layer method, and obtaining the edge weight coefficient; Step S120: constructing a causal structure graph according to the dynamic process parameters, the waviness characteristic data and the edge weight coefficients.

[0034] In this embodiment, by first obtaining the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, the correlation between the dynamic process parameters and the waviness characteristic data is calculated by the multi-head graph attention layer method to obtain the edge weight coefficient; then, according to the dynamic process parameters, the waviness characteristic data and the edge weight coefficient, a causal structure graph is constructed, so as to calculate the correlation between the process parameters and the waviness characteristic data, construct a causal structure graph, provide a solid foundation for subsequent correction, effectively reduce measurement errors, improve the accuracy of waviness measurement, and make the measurement result closer to the actual surface waviness condition of the workpiece.

[0035] Specifically, in step S110, the dynamic process parameters include tool face wear amount, dominant vibration frequency, feed rate, and spindle thermal elongation.

[0036] The tool flank wear is monitored in real time by a contact displacement sensor such as a laser probe. A piezoelectric or capacitive acceleration sensor is selected and tightly installed at a position close to the vibration source such as the spindle bearing housing to convert the vibration mechanical quantity into an electrical signal. The signal is collected at high speed by a data acquisition card, and then the signal is subjected to a fast Fourier transform by spectrum analysis software such as MATLAB or LabVIEW to separate different frequency components and determine the dominant vibration frequency. The real-time feed speed of the machine tool CNC system is read, and the feed speed includes the original speed curve in the acceleration and deceleration stages, including but not limited to trapezoidal acceleration and deceleration, S-shaped acceleration and deceleration.

[0037] The spindle thermal elongation is measured by deploying thermocouple sensors on the machine tool spindle box and the workpiece fixture and combining with a laser displacement sensor. Measuring the spindle thermal elongation is a prior art, and the specific test method is as follows: The spindle thermal elongation is the axial length expansion of the spindle system due to temperature rise during operation. The thermocouple sensors are installed on the machine tool spindle box and the workpiece fixture and can measure the temperature change of the spindle during processing in real time; the working principle of the thermocouple is based on the Seebeck effect, that is, an electromotive force difference will be generated at the contact point of two different metals when the temperature changes, and the temperature value can be obtained by measuring this electromotive force difference; the laser displacement sensor measures the displacement of the spindle by emitting a laser beam to the spindle surface and receiving the reflected light. By establishing a temperature-displacement relationship model, the thermal elongation of the spindle can be calculated according to the temperature change.

[0038] The waviness characteristic data includes wave height, wavelength, and waviness distribution.

[0039] By using a white light interferometer to scan the surface of the workpiece, a grid point cloud is obtained (the spatial resolution is less than or equal to 10 ), calculate the waviness characteristic data of the calculation area. The wave height H represents the vertical distance between the highest point and the lowest point on the surface within a certain measurement area, that is, the peak-valley difference within the local area r, where the local area r is the measurement area of the white light interferometer, and the unit of the peak-valley difference is .

[0040] The wavelength L is the wavelength corresponding to the dominant ripple period extracted by two-dimensional Fourier transform; the waviness distribution (x, y): mark the wave height value and wavelength value of each grid point according to the processing time to form a spatio-temporal matrix.

[0041] In this embodiment, in order to ensure the accuracy of the waviness characteristic data and not affect subsequent processing, the waviness characteristic data also needs to go through time series alignment, missing value processing, data cleaning, and standardization processing.

[0042] Specifically, time series alignment is to bind the waviness characteristic data of each workpiece to the processing period [t start , t end , extract the mean / extreme value of the dynamic factors within the corresponding period, and form corresponding data.

[0043] Missing value processing is to check whether there are missing values in the data. During the acquisition of the spindle vibration mode data, some data may be missing due to reasons such as temporary sensor failures. For missing values, if the missing ratio is small, linear interpolation, polynomial interpolation and other methods can be used to fill them according to the time series characteristics of the data; if the missing ratio is large, those skilled in the art will comprehensively consider the importance and integrity of the data and decide whether to discard this part of the data or re-acquire it.

[0044] Data cleaning is to detect outliers in the collected various data. For example, in the tool wear amount data, if the wear amount increases sharply within a short time and exceeds the reasonable range, it may be caused by sensor failures or other abnormal factors and needs to be marked and processed. For such outliers, those skilled in the art can use statistical methods such as to judge, that is, if the data point deviates from the mean by more than 3 times the standard deviation, it is regarded as an abnormal value. For abnormal values, those skilled in the art can choose to delete them, replace them with the mean of adjacent time points as a reasonable value, etc. according to the actual situation.

[0045] After completing the data cleaning, in order to eliminate the differences in dimension and order of magnitude of different data features and make each feature have the same importance in subsequent analysis and model training, the data is standardized, that is, when performing the step of calculating the correlation between the dynamic process parameters and the waviness characteristic data by the multi-head graph attention layer method in step S110, the data is already the data after being standardized.

[0046] In one embodiment, in step S110: The correlation between the dynamic process parameters and the waviness feature data is calculated by the multi-head graph attention layer method to obtain the edge weight coefficient, specifically as follows: In the multi-head graph attention layer method, node feature encoding: The node parameters (dynamic process parameters and waviness features) are converted into high-dimensional vectors , for example, when considering the wear amount in the previous 2 time steps, , where is the high-dimensional vector related to the dynamic process parameters, represents the values of the dynamic process parameters (such as flank wear amount, dominant vibration frequency, feed rate, and thermal deformation influence period) at different time points t, is the value of the dynamic process parameters at the previous time step, is the value of the dynamic process parameters at the previous two time steps.

[0047] Attention coefficient calculation: Calculate the importance of the neighbor nodes of the node node parameters , and the specific formula is as follows: , where is the attention coefficient; the symbols i and j are general mathematical notations representing nodes, is the trainable attention weight vector, responsible for capturing the correlation between the dynamic process parameters and the waviness feature data; and are the feature vectors of the node and its neighbor node respectively, represents concatenating the feature vectors of nodes and along the feature dimension to fuse the information of both, is to linearly map the feature vectors of nodes and from the d-dimensional space to the d-dimensional space through matrix multiplication. The purpose is to enhance the features and improve the expression ability; LeakyReLU is the activation function, used to introduce non-linearity and avoid gradient disappearance. The formula is ( is a small constant, such as 0.2), where k is the index of the neighbor node and W is the learnable weight matrix. The learnability of W is one of the core designs of the graph attention layer, and its role is to adaptively adjust the node features through linear transformation to better calculate the attention and aggregate the neighbor information. In this formula, the numerator amplifies the difference through the function, and the denominator normalizes all the neighbor nodes of , and finally represents​​​​​ For the relative importance, the value range is in .

[0048] Next, perform weight update, specifically the edge weight calculation based on multi-head attention fusion. Assuming there are h attention heads in total, update the edge weights as follows: , where represents the final edge weight between nodes i and j, which is a value measuring the association strength between the two nodes after multi-head attention fusion; represents the number of "heads" in the multi-head attention mechanism, that is, the number of attention sub-models for parallel computing. is the summation symbol, indicating that for the values range from 1 to all terms are accumulated; The superscript of represents the th attention head, and the subscript

[0049] represents the attention coefficient of node i to node j, reflecting the relative importance of node j to i in this head. , indicating the influence of tool wear on wave height), its corresponding attention coefficient is relatively large. After softmax calculation, the weight will also be significantly higher than that of the secondary link (such as other parameter links with less influence on wave height). In this way, the model will pay more attention to the high-frequency influence link, highlighting the role of key factors in the result, and improving the accuracy and effectiveness of causal relationship modeling. For example, in actual machining, the influence of tool wear on wave height is often crucial. Through this weight update method, this link can occupy a more important position in the model, so as to more accurately capture and express this causal relationship.

[0050] Next, construct the causal structure graph as follows: Among them, the definitions of nodes and edges in G(V, E) are: The node set V represents the set containing process parameter nodes and waviness feature nodes. The specific process parameter nodes include: V W (tool wear amount), V A (vibration frequency), V V (feed rate), V D (thermal deformation amount). The waviness feature nodes are V H , V L corresponding to wave height and wavelength respectively.

[0051] E is the set of directed edges, and the initial edges are preset by physical mechanisms as follows: ​

[0052] Among them, (Tool wear → Wave height): In turning machining, as the tool continuously cuts (such as machining 100 parts), the flank wear of the tool gradually increases. After the tool wears and becomes dull, the cutting force increases and becomes unstable, resulting in a significant rise in the wave height of the machining marks on the workpiece surface.

[0053] (Vibration frequency → Wavelength): In milling machining, if the spindle vibration frequency suddenly increases due to equipment failure (such as from 50 to 200 ), the relative movement rhythm between the tool and the workpiece is disrupted. At this time, the wavelength of the machining surface ripples will show obvious fluctuations, and the original uniform wavelength becomes uneven, with some areas shortened to , and some areas extended to .

[0054] (Feed rate → Wave height): In numerical control machining, if the feed rate suddenly increases, the cutting force instantaneously increases and the cutting process becomes unstable, which causes the wave height of the workpiece surface to increase sharply. (Thermal deformation → Wave height): After long-term milling machining, the spindle of the machine tool undergoes thermal deformation . The thermal deformation changes the relative position between the tool and the workpiece, resulting in uneven cutting depth, and ultimately causing the wave height of the workpiece surface to increase abnormally.

[0055] The attributes of the edge include: edge weight , representing the influence intensity, optimized through the graph attention mechanism, with a value range of [0, 1]). It also includes the lag time, which is the delay time from the parameter change to the abnormal waviness.

[0056] In one embodiment, step S200: Real-time collect environmental impact data and the surface waviness data of the workpiece, and determine whether the surface waviness data exceeds a preset waviness threshold. If the determination is yes, obtain abnormal waviness data, which specifically includes: First, collect the real-time surface waviness data of the workpiece, use a high-resolution topography measurement system such as a 3D laser scanner or a white light interferometer to perform a grid scan on the workpiece surface, collect the real-time waviness data, and obtain the wave height at each grid point , wavelength , and spatial resolution m.

[0057] Next, threshold comparison and signal processing are performed. Among them, abnormal wave height: the preset wave height threshold is m. If m, it is marked as abnormal wave height; abnormal wavelength: set the target wavelength . If , it is marked as abnormal wavelength; spatial filtering: separate high-frequency noise through Gaussian filtering or a band-pass filter to obtain a pure waviness signal.

[0058] If an anomaly is detected, waviness anomaly data is output. Among them, the spatial coordinates of the abnormal area: represented by grid coordinates or geometric contours, such as a rectangular area ; anomaly type label: clearly marked as "abnormal wave height", "abnormal wavelength", or "compound anomaly"; quantification indicators such as abnormal wave height value: (such as ); the abnormal wavelength value is expressed as .

[0059] In one embodiment, in step S200, after determining whether the surface waviness data exceeds the preset waviness threshold, it further includes: if the determination is negative, it is determined that the surface waviness data is normal.

[0060] In one embodiment, step S300: input the waviness anomaly data into a causal structure map, analyze the waviness anomaly data based on the causal structure map, and obtain the influence paths of the main process factors and the influence paths of the secondary process factors; including: Step S310: input the waviness anomaly data into the causal structure map, and use the graph convolutional network method in the causal structure map for reverse reasoning to obtain the process parameter responsibility factors; Step S320: use the Bayesian inference method to screen the process parameter responsibility factors to obtain the main process factors and the secondary process factors; Step S330: respectively obtain the influence paths of the main process factors and the influence paths of the secondary process factors by querying the causal structure map.

[0061] In one embodiment, the abnormal corrugation data is input into a causal structure graph in turn, and reverse reasoning is performed in the causal structure graph using a graph convolution network method to obtain a process parameter responsibility factor; the process parameter responsibility factor is screened using a Bayesian reasoning method to obtain a main process factor and a secondary process factor; the influence path of the main process factor and the influence path of the secondary process factor are obtained by querying the causal structure graph, respectively, so as to accurately determine the abnormal corrugation situation, and starting from the abnormal node, through graph convolution operations and Bayesian reasoning, in-depth analysis is performed to find out the main and secondary process factors that cause the abnormality and their causal influence paths, and the correction amounts of the main and secondary causes are calculated in a targeted manner, so as to achieve effective correction of the abnormal corrugation, improve the stability and reliability of the production process, and reduce production interruptions and defective rates caused by corrugation problems.

[0062] First, the abnormal waviness data is input into the causal structure map, and reverse reasoning is performed in the causal structure map G(V,E) to locate the process parameter responsibility factor that causes the abnormality. Among them, the abnormal node activation is to map the abnormal type label to the corresponding node of the causal structure map (such as wave height abnormal activation, wavelength abnormal activation), and the initial abnormal intensity of the abnormal node is set , the remaining nodes The abnormal signal is propagated layer by layer to the upstream process parameter node through the graph convolutional network (GCN). Upstream process parameter nodes with incoming edge connections , calculate its abnormal intensity, the specific formula is as follows:

[0063] in, is abnormal intensity, is the edge weight, is the initial abnormal strength of the abnormal node, Points to abnormal nodes The edge set of For Node The number of outgoing edges, which is used for normalization to avoid score overflow; The process parameter responsibility factor is derived from the process parameter node , including V W (tool wear), V A (vibration frequency), V V (feed rate), V D (Thermal deformation).

[0064] Causal path screening and priority sorting are path compression, Bayesian reasoning and posterior probability calculation. Among them, path compression is to remove weight Weakly related links, reducing redundant reasoning (such as only keeping The edges); Bayesian inference is to calculate the posterior probability of each process parameter node by combining the anomaly intensity data and historical data, and screen out the top 2 factors with the highest anomaly contribution The posterior probability is calculated as follows:

[0065] Among them, is the anomaly intensity, i refers to the i-th process factor node, which is a counting symbol, is the edge weight, is the weight from node n to node j, calculated by the multi-head graph attention layer, representing the influence intensity of the process parameter on the waviness feature ; is the prior probability, based on historical data statistics, such as the prior probability of tool wear anomaly , the prior probability of spindle vibration frequency anomaly etc.; The numerator represents the observed joint probability, that is, the prior probability multiplied by the likelihood probability; The denominator is a summation operation, which sums over all nodes that satisfy ( represents a certain set of nodes related to ) and (edge weight threshold), which is the total probability observed under all assumptions, and can also be understood as the marginal probability, is the number of nodes, is the anomaly intensity of the n-th node, is the prior probability of the n-th node.

[0066] Sorted in descending order according to the posterior probability , select the top 2 factors as the main and secondary process factors. If (the highest), then is the main factor; if (the second highest), then is the secondary factor.

[0067] The obtained main process factor is the tool wear amount (posterior probability ), and the secondary process factor is the spindle vibration frequency (posterior probability ). Then the output result is that the tool wear exceeds the limit (corresponding to node , weight , lag time 15 minutes); spindle vibration frequency anomaly (corresponding to node , weight , Lag time: 5 minutes); By querying the causal structure map, the influence paths of the main process factors and the influence paths of the secondary process factors are obtained respectively, as well as the weights and weights of the specific values.

[0068] Influence path of the main process factor: : Tool wear → abnormal wave height, path description: "Tool wear causes the cutting edge to become blunt, the cutting force fluctuates greatly, and the wave height exceeds the standard", weight Obtained through edge weight to get the specific value; Influence path of the secondary process factor: : Vibration frequency → abnormal wavelength, path description: "Increased spindle vibration leads to unstable relative movement between the tool and the workpiece, and the wavelength fluctuates periodically", weight Obtained through edge weight to get the specific value.

[0069] In one embodiment, in step S400, according to the main process factor and the influence path of the main process factor, a waviness correction value is generated, including: Step S411: According to the main process factor and the influence path of the main process factor, generate a main cause correction value through the adaptive projection algorithm; Step S412: According to the secondary process factor and the influence path of the secondary process factor, calculate and generate a secondary cause correction value through the adaptive projection algorithm; Step S413: Calculate the waviness correction value according to the main cause correction value and the secondary cause correction value.

[0070] In one embodiment, in the above description, the main process factor (tool wear amount) and the secondary process factor (spindle vibration frequency) have been clearly defined, and now the abnormal data is corrected collaboratively based on both. The correction of the main process factor is through the main process factor and the influence path of the main process factor , and the main cause correction value is calculated through the adaptive projection algorithm.

[0071] Calculate the correction amount :

[0072] Among them, is the main cause correction amount, which is the correction amount of tool wear on the wave height, is the influence weight of tool wear on the wave height, is the influence weight of vibration frequency on the wavelength. is the standard wave height value, is the coordinate The abnormal wave height value at a certain point. Among them, the influence weight of the vibration frequency on the wavelength is introduced , in order to achieve a reasonable distribution of the correction amount through the weight ratio relationship, reflect the relative influence of the primary and secondary factor weights, and ensure that the correction calculation conforms to the balance of the overall weight system.

[0073] According to the primary factor correction amount and abnormal data, the primary factor correction value is calculated as follows:

[0074] Among them, is the primary factor correction value, is the coordinate of the abnormal wave height value, is the primary factor correction amount, the primary factor dynamic scaling factor , the higher the primary factor weight, the larger the value of

[0075] The secondary factor (main shaft vibration frequency ) correction is based on the secondary process factor main shaft vibration frequency and the influence path of the secondary process factor , and the secondary factor correction value is calculated through the adaptive projection algorithm. The specific calculation formula is as follows:

[0076] Among them, is the secondary factor correction amount, is the influence weight of tool wear on the wave height, is the weight using the influence weight of vibration frequency on the wavelength; is the standard target wavelength (such as 2mm). is the coordinate of the abnormal wavelength value at a certain point; is the influence weight of tool wear on the wave height.

[0077] , among them, is the secondary factor correction value, is the coordinate of the abnormal wavelength value, is the secondary factor correction amount, is the secondary factor dynamic scaling factor, the lower the secondary factor weight, the smaller the value of

[0078] The adaptive superposition correction formula is used in the waviness correction process to perform independent corrections for different influencing factors (such as process parameters, environmental factors, etc.) respectively to obtain parallel correction values, specifically as follows: , Among them, is the waviness correction value, is the main factor correction value, is the main factor dynamic scaling factor, is the secondary factor correction value; it is iteratively adjusted according to the residual error after correction, is the secondary factor dynamic scaling factor, is the main factor correction amount, is the secondary factor correction amount. This correction method distinguishes the main factor from the secondary factor, combines their respective weights and dynamic scaling factors, and more accurately corrects the abnormal area for multi-factor collaborative correction, improving the pertinence and accuracy of error correction.

[0079] In one embodiment, in step S400, the waviness correction value is calculated based on the environmental impact data and the waviness correction value, including: Step S421: Generate an environmental impact coefficient based on the environmental impact data; Specifically, step S421: Generating an environmental impact coefficient based on the environmental impact data includes: Step S4211: Standardize the environmental impact data and generate standardized environmental data; Step S4212: Generate an environmental impact coefficient based on the preset Gaussian process regression and the standardized environmental data.

[0080] The environmental impact data includes humidity, cutting fluid performance, and viscosity. For humidity, the environmental relative humidity is collected through a humidity sensor, and the influence of humidity on the moisture absorption and expansion of the workpiece material (such as for aluminum alloy, when the humidity increases by 10%, the linear expansion coefficient increases ) and the evaporation rate of the cutting fluid is analyzed. For the cutting fluid performance, the concentration of the water-based cutting fluid is measured through a conductivity meter. Insufficient concentration (such as 5% lower than the standard value) will lead to insufficient lubrication and exacerbate tool wear; for viscosity, the viscosity of the cutting fluid is detected using a rotational viscometer. Abnormal viscosity (such as 20% higher than the standard value) will affect the chip evacuation effect and cause spindle vibration.

[0081] The humidity, cutting fluid performance, and viscosity are standardized and converted into dimensionless standardized values. Specifically, the humidity standardization is as follows:

[0082] Among them, is the standardized humidity, is the standard humidity, is the maximum humidity, is the minimum humidity.

[0083] The normalization of the concentration is as follows:

[0084] where, is the concentration after normalization, is the standard concentration, is the maximum concentration, is the minimum concentration.

[0085] The normalization of the viscosity is as follows:

[0086] where, is the viscosity after normalization, is the standard viscosity, is the maximum viscosity, is the minimum viscosity.

[0087] Next, a Gaussian process regression (GPR) is used to model the non - linear relationship between factors and output the environmental impact coefficient:

[0088] where, is the environmental impact coefficient, ; is the concentration after normalization; is the humidity after normalization, () represents the Gaussian process regression function; If , it indicates that the influence of environmental factors (humidity, concentration, viscosity, etc.) on waviness is almost negligible, and the waviness correction is mainly dominated by process parameters (such as tool wear, vibration frequency, etc.).

[0089] If , it means that the influence of environmental factors on waviness reaches the maximum, and the comprehensive effect of environmental factors needs to be fully considered when correcting waviness.

[0090] If , it reflects that environmental factors have a certain degree of influence on waviness. The larger the value, the more significant the influence of environmental factors. For example, in a humid environment (high ), abnormal cutting fluid concentration (deviating from the standard value) or viscosity change ( fluctuation), through the Gaussian process regression and the squared - exponential kernel function to model the non - linear correlation of these normalized environmental factors, the output It will increase accordingly, indicating that it is necessary to strengthen the compensation and correction of environmental factors.

[0091] If EIC > 1 appears, it belongs to data anomaly or model failure. Those skilled in the art shall check whether the measured values of environmental factors exceed the limit and whether the standardized parameters are reasonable, and make adaptive adjustments according to the actual situation. This application will not give examples or elaborations.

[0092] It should be understood that quantifies the comprehensive influence degree of environmental factors on waviness, provides a basis for calculating the environmental compensation amount in subsequent waviness correction, and makes the correction more in line with the actual processing scenario.

[0093] Step S422: Calculate the environmental compensation value according to the influence degree of the environmental influence coefficient on waviness; Step S423: Calculate the waviness correction value according to the waviness correction value and the environmental compensation value.

[0094] In one embodiment, first, a non - linear compensation model is constructed according to the influence degree of the environmental influence coefficient (EIC) on waviness. Considering the difference in the influence degree of different EIC intervals on waviness, a piece - wise function is used to achieve more accurate compensation.

[0095] , wherein, is the environmental compensation value at is the environmental influence coefficient, is the waviness correction value; , the value of k1 is obtained by those skilled in the art through fitting a large amount of historical data and experimental verification, representing the influence coefficient of environmental influence on waviness in this interval. It should be understood that when the environmental influence is small, the compensation amount increases linearly with the increase of EIC and is proportional to the waviness correction value.

[0096] , is the environmental compensation value at is the environmental influence coefficient, is the waviness correction value; , the value of k2 is obtained by those skilled in the art through fitting a large amount of historical data and experimental verification, representing the influence coefficient of environmental influence on waviness in this interval. By this method, when the environmental influence is at a medium level, the waviness can be corrected more effectively because the influence of environmental factors may be more complex at this time, and the quadratic function can better capture this change.

[0097] , Among them, is the environmental compensation value at that time, , in the case of strong environmental impact, it can fully adjust the waviness to ensure the final measurement accuracy.

[0098] Combining the waviness correction value and the environmental compensation value, the final waviness correction value is calculated as follows:

[0099] Among them, is the waviness correction value, is the waviness correction value, is the environmental compensation value in the i-th case.

[0100] By outputting the final waviness correction value, which is presented in matrix form corresponding to the coordinates of each measurement point on the workpiece surface, ensuring consistency with the previous measurement data structure for convenient subsequent analysis and use. At the same time, the value of the environmental impact coefficient EIC is output, as well as the compensation interval and compensation formula used in the calculation process for easy traceability and verification of the results. For the case where EIC is greater than 0.7, "Significant environmental impact, the correction value is greatly affected by environmental factors" is marked in the result to remind relevant personnel to pay attention to the impact of environmental factors on the measurement results.

[0101] Therefore, the waviness measurement accuracy correction method described in this application collects dynamic process parameters and waviness characteristic data, constructs a causal structure map using advanced algorithms, accurately analyzes abnormal waviness data, finds out the main and secondary process factors and causal influence paths, and calculates the correction amount in combination with the adaptive projection algorithm. At the same time, considering the environmental impact data, calculates the environmental impact coefficient, and finally obtains an accurate waviness correction value. This method comprehensively and systematically solves the problem of waviness measurement accuracy, fully considering the influences of process parameters, abnormal data processing, and environmental factors, etc.

[0102] In one embodiment, as Figure 2 shown, there is also provided an artificial intelligence-based waviness measurement accuracy correction system, and the system includes: A causal map construction module, configured to obtain the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, and construct a causal structure map according to the dynamic process parameters and the waviness characteristic data; An abnormal data acquisition module, configured to collect environmental impact data and the surface waviness data of the workpiece in real time, and determine whether the surface waviness data exceeds a preset waviness threshold. If the determination is yes, waviness abnormal data is obtained; Anomaly data analysis module, configured to input the waviness anomaly data into a causal structure map, analyze the waviness anomaly data based on the causal structure map, and obtain the influence paths of the main process factors and the influence paths of the secondary process factors; Environmental impact correction module, configured to generate a waviness correction value according to the main process factors and the influence paths of the main process factors, and calculate a waviness correction value according to the environmental impact data and the waviness correction value.

[0103] In one embodiment, the anomaly data analysis module is further configured to: input the waviness anomaly data into a causal structure map, perform reverse reasoning using a graph convolutional network method in the causal structure map to obtain process parameter responsibility factors; screen the process parameter responsibility factors using a Bayesian inference method to obtain main process factors and secondary process factors; and respectively obtain the influence paths of the main process factors and the influence paths of the secondary process factors by querying the causal structure map.

[0104] In one embodiment, the environmental impact correction module is further configured to: generate a main cause correction value according to the main process factors and the influence paths of the main process factors through an adaptive projection algorithm; calculate and generate a secondary cause correction value according to the secondary process factors and the influence paths of the secondary process factors through an adaptive projection algorithm; and calculate a waviness correction value according to the main cause correction value and the secondary cause correction value.

[0105] In one embodiment, the environmental impact correction module is further configured to: generate an environmental impact coefficient according to the environmental impact data; calculate an environmental compensation value according to the influence degree of the environmental impact coefficient on the waviness; and calculate a waviness correction value according to the waviness correction value and the environmental compensation value.

[0106] In one embodiment, the environmental impact correction module is further configured to: perform normalization processing on the environmental impact data and generate normalized environmental data; and generate an environmental impact coefficient based on a preset Gaussian process regression and the normalized environmental data.

[0107] In one embodiment, the causal map construction module is further configured to: obtain the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, calculate the correlation between the dynamic process parameters and the waviness characteristic data through a multi-head graph attention layer method to obtain edge weight coefficients; and construct a causal structure map according to the dynamic process parameters, the waviness characteristic data, and the edge weight coefficients.

[0108] In one embodiment, the anomaly data acquisition module is further configured to: determine whether the surface waviness data exceeds a preset waviness threshold, and then, if the determination result is negative, determine that the surface waviness data is normal.

[0109] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for correcting the accuracy of waviness measurement based on artificial intelligence are implemented.

[0110] In one embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for correcting the accuracy of waviness measurement based on artificial intelligence are implemented.

[0111] It should be noted that for the information interaction, execution process, etc. between the above-mentioned modules, since they are based on the same concept as the method embodiment of the present application, the specific functions and the technical effects brought by them can be specifically referred to in the method embodiment part, and will not be elaborated here.

[0112] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0113] It should be noted that for the information interaction, execution process, etc. between the above-mentioned modules, since they are based on the same concept as the method embodiment of the present application, the specific functions and the technical effects brought by them can be specifically referred to in the method embodiment part, and will not be elaborated here.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated herein.

[0115] An embodiment of this application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, the steps in any of the foregoing method embodiments are implemented.

[0116] An embodiment of this application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

[0117] An embodiment of this application provides a computer program product, and when the computer program product runs on a mobile terminal, the mobile terminal is enabled to implement the steps in the foregoing method embodiments when executed.

[0118] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0119] In the above embodiments, the descriptions of the various embodiments have their own focuses. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0121] In the embodiments provided in this application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0122] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0124] An embodiment of the present application also provides a computer device. The computer device of this embodiment includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, it implements the steps in any of the above embodiments of the method.

[0125] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above description is an example of a computer device and does not constitute a limitation on the computer device. It may include more or fewer components than the above description, or combine some components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0126] The so-called processor may be a central processing unit (CPU), and this processor 0 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0127] In some embodiments, the memory may be an internal storage unit of the computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device. Further, the memory may also include both the internal storage unit and the external storage device of the computer device. The memory is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is to be output.

[0128] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0129] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for correcting the measurement accuracy of waviness based on artificial intelligence, characterized in that, The method includes: Obtaining the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, and constructing a causal structure graph according to the dynamic process parameters and the waviness characteristic data; Real-time collecting the environmental impact data and the surface waviness data of the workpiece, and judging whether the surface waviness data exceeds a preset waviness threshold. If the judgment is yes, waviness abnormal data is obtained; Inputting the waviness abnormal data into the causal structure graph, analyzing the waviness abnormal data based on the causal structure graph, and obtaining the influence paths of the main process factors and the influence paths of the secondary process factors; Generating a waviness correction value according to the main process factors and the influence paths of the main process factors, and calculating a waviness correction value according to the environmental impact data and the waviness correction value.

2. The method for correcting the measurement accuracy of waviness based on artificial intelligence according to claim 1, wherein Inputting the waviness abnormal data into the causal structure graph, analyzing the waviness abnormal data based on the causal structure graph, and obtaining the influence paths of the main process factors and the influence paths of the secondary process factors; includes: Inputting the waviness abnormal data into the causal structure graph, and using the graph convolutional network method in the causal structure graph for reverse reasoning to obtain the process parameter responsibility factors; Using the Bayesian inference method to screen the process parameter responsibility factors to obtain the main process factors and the secondary process factors; By querying the causal structure graph, respectively obtaining the influence paths of the main process factors and the influence paths of the secondary process factors.

3. The method for correcting the measurement accuracy of waviness based on artificial intelligence according to claim 1, wherein Generating a waviness correction value according to the main process factors and the influence paths of the main process factors, includes: Generating a main cause correction value through an adaptive projection algorithm according to the main process factors and the influence paths of the main process factors; Calculating and generating a secondary cause correction value through an adaptive projection algorithm according to the secondary process factors and the influence paths of the secondary process factors; Calculating and obtaining a waviness correction value according to the main cause correction value and the secondary cause correction value.

4. The method for correcting the measurement accuracy of waviness based on artificial intelligence according to claim 1, wherein Calculating and obtaining a waviness correction value according to the environmental impact data and the waviness correction value, includes: Generating an environmental impact coefficient according to the environmental impact data; Calculating an environmental compensation value according to the influence degree of the environmental impact coefficient on the waviness; Calculating and obtaining a waviness correction value according to the waviness correction value and the environmental compensation value.

5. The method for correcting the measurement accuracy of waviness based on artificial intelligence according to claim 4, wherein Generating an environmental impact coefficient according to the environmental impact data, includes: Performing normalization processing on the environmental impact data and generating normalized environmental data; Generating an environmental impact coefficient based on a preset Gaussian process regression and the normalized environmental data.

6. The method for correcting the measurement accuracy of waviness based on artificial intelligence according to claim 1, wherein Obtaining the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, and constructing a causal structure graph according to the dynamic process parameters and the waviness characteristic data; includes: Obtaining the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, calculating the correlation between the dynamic process parameters and the waviness characteristic data through the multi-head graph attention layer method to obtain an edge weight coefficient; Constructing a causal structure graph according to the dynamic process parameters, the waviness characteristic data and the edge weight coefficient.

7. The method for correcting the measurement accuracy of waviness based on artificial intelligence according to claim 1, characterized in that, Judging whether the surface waviness data exceeds a preset waviness threshold, and then further includes: If the judgment is negative, it is determined that the surface waviness data is normal.

8. An artificial intelligence-based waviness measurement accuracy correction system, characterized in that, The system includes: A causal graph construction module, configured to obtain the dynamic process parameters of the machine tool and the waviness characteristic data of the workpiece when the machine tool processes the workpiece, and construct a causal structure graph according to the dynamic process parameters and the waviness characteristic data; An abnormal data acquisition module, configured to collect environmental impact data and the surface waviness data of the workpiece in real time, determine whether the surface waviness data exceeds a preset waviness threshold, and if the judgment is positive, obtain waviness abnormal data; An abnormal data analysis module, configured to input the waviness abnormal data into the causal structure graph, analyze the waviness abnormal data based on the causal structure graph, and obtain the influence path of the main process factor and the influence path of the secondary process factor; An environmental impact correction module, configured to generate a waviness correction value according to the main process factor and the influence path of the main process factor, and calculate a waviness correction value according to the environmental impact data and the waviness correction value.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images